Abstract
The article describes the use of a self-learning neural network of the SOM type to forecast insolvency of enterprises in construction industry. The research was carried out on the basis of information regarding 578 enterprises that went into bankruptcy in the years 2007–2013. These entities constituted a sample singled out from a population of 4750 enterprises that went bankrupt in Poland during that time, for which it was possible to obtain financial statements in the form of balance sheets and profit-and-loss accounts for the period of 5 years prior to the bankruptcy. Twelve (12) variables in the form of financial analysis indicators have been assessed, which are most commonly used in the systems of early warning about insolvency. The network constructed allowed effective classification of nearly all entities as insolvent a year before the announcement of their bankruptcy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
International-wise, a synthetic description of the functionality of bankruptcy registers of EU member states, which in the future is to become a centralized database system, is available on the European Justice Web site: https://beta.e-justice.europa.eu/110/PL/bankruptcy_and_insolvency_registers; (accessed on: September 11, 2018).
- 2.
In accordance with the adopted research methodology, described in the first part of the study, the construction enterprises that went bankrupt in the years 2007–2013 have been described by financial analysis indicators and subjected to the indicator analysis. The indicators that required averaging of the balance sheet values, which directly results from the calculation procedure used in the financial analysis, should contain data for the reporting periods even 5 years prior to the year in which the bankruptcy took place. This often caused numerous data gaps, because despite the obligatory submission of such documents to the commercial courts, the entities subjected to restructuring transformations, particularly those at risk of bankruptcy, did not meet this obligation. The lack of sanctioning of the law in this aspect poses a big problem for the development of research on the models of early warning about bankruptcy, because it prevents acquisition of financial data regarding these entities, see e.g., [30].
- 3.
This risk was materialized in the form of a court ruling on the bankruptcy of these entities in the (t0) period.
References
Ustawa z dnia 28 lutego 2003 r. Prawo upadłościowe, Dz.U. 2003 nr 60 poz. 535
Ustawa z dnia 15 maja 2015 r. Prawo restrukturyzacyjne, Dz.U. 2015 poz. 978
Regulation (EU) 2015/848 of the European Parliament and of the Council of 20 May 2015 on insolvency proceedings OJ L 141, 5.6.2015, 19–72; (http://data.europa.eu/eli/reg/2015/848/oj; dostęp z dnia: 10.09.2018)
Czapracka, A., Babiarz-Mikulska, K., Morawska, S.: Ocena efektywności procedur upadłościowych wobec przedsiębiorców. Difin, Warszawa (2012)
Kitowski, J.: Metody dyskryminacyjne jako instrument oceny zagrożenia upadłością przedsiębiorstwa, Rzeszów, Wydawnictwo Uniwersytetu Rzeszowskiego, 12–23 (2015)
Balicki, A.: Statystyczna analiza wielowymiarowa i jej zastosowania społeczno-ekonomiczne, Gdańsk 2009, Wydawnictwo Uniwersytetu Gdańskiego, 20–23 (2009)
Antonowicz, P.: Bankructwa i upadłości przedsiębiorstw. Teoria – praktyka gospodarcza – studia regionalne. Wydawnictwo Uniwersytetu Gdańskiego, Gdańsk (2015)
Antonowicz, P.: Zmienne egzogeniczne funkcji dyskryminacyjnych w polskich modelach prognozowania upadłości przedsiębiorstw. In: Balcerzak, A.P., Rogalska, E. (eds.) Stymulowanie innowacyjności i konkurencyjności przedsiębiorstwa w otoczeniu globalnej gospodarki wiedzy. Wydawnictwo Naukowe Uniwersytetu Mikołaja Kopernika, Toruń (2010)
Kohonen, T.: Self-organizing formation of topologically correct feature maps. Biol. Cybern. 43(1), 59–69 (1982)
Alahakoon, D., Halgamuge, S.K., Sirinivasan, B.: Dynamic self organizing maps with controlled growth for knowledge discovery. IEEE Trans. Neural Networks, Spec. Issue Knowl. Disc. Data Min. 11, 601–614 (2000)
Rauber, A., Merkl, D., Dittenbach, M.: The growing hierarchical self-organizing map: exploratory analysis of high-dimensional data. IEEE Trans. Neural Networks 13(6), 1331–1341 (2002)
Martinetz, T., Schulten, K.: A neural gas network learns topologies. In: Artificial Neural Network, pp. 397–402. Elsevier (1991)
Fritzke, B.: A growing neural gas network learns topologies. In: Tesauro, G., Touretzky, D.S., Leen, T.K. (eds.) Advances in Neural Information Processing Systems, vol. 7, pp. 625–632. MIT Press, Cambridge (1995)
Migdał-Najman, K., Najman, K.: Samouczące się sztuczne sieci neuronowe w grupowaniu i klasyfikacji danych, Teoria i zastosowania w ekonomii. Wydawnictwo Uniwersytetu Gdańskiego, Gdańsk (2013)
Kaski, S., Kangas, J., Kohonen, T.: Bibliography of self-organizing map (SOM) papers: 1981–1997. Neural Comput. Surv. 1, 102–350 (1998)
Decker, R.: Market basket analysis by means of a growing neural network. Int. Rev. Retail Distrib. Consum. Res. 15(2), 151–169 (2005)
Decker, R., Monien, K.: Market basket analysis with neural gas networks and self-organising maps. J. Target. Meas. Anal. Mark. 11(4), 373–386 (2003)
Migdał-Najman, K.: Analiza porównawcza samouczących się sieci neuronowych typu SOM i GNG w poszukiwaniu reguł asocjacyjnych, Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu. Taksonomia 18. Klasyfikacja i analiza danych - teoria i zastosowania, 176, 272–281 (2011)
Migdał-Najman, K.: Badowska S. Wykorzystanie samouczących się sieci neuronowych w analizie zachowań zakupowych i identyfikacji ich wzorców wśród konsumentów w wieku 60 lat i więcej. Zarządzanie i Finanse 3, 295–307 (2017)
Serrano-Cinca, C.: Self organizing neural networks for financial diagnosis. Decis. Support Syst. 17(3), 227–238 (1996)
Séverin, E.: Self organizing maps in corporate finance: quantitative and qualitative analysis of debt and leasing. Neurocomputing 73(10–12), 2061–2967 (2010)
Chen, N., Ribeiro, B., Vieira, A., Chen, A.: Clustering and visualization of bankruptcy trajectory using self-organizing map. Expert Syst. Appl. 40(1), 385–393 (2013)
Migdał Najman, K., Najman, K.: Diagnozowanie kondycji finansowej spółek notowanych na GPW w Warszawie w oparciu o sieć SOM, Zeszyty Naukowe nr 389, Rynek Kapitałowy, Skuteczne Inwestowanie, część I, Wydawnictwo Naukowe Uniwersytetu Szczecińskiego, Szczecin, 507–519 (2004)
Corridoni, J.M., Bimbo, A., Landi, L.: 3D object classification using multi-object Kohonen networks. Pattern Recogn., Pergamon 29(6), 919–935 (1996)
Ye, H., Lo, B.W.N.: A visualised software library: nested self-organizing maps for retrieving and browsing reusable software assets. Neural Comput. Appl. 9(4), 266–279 (2000)
Deboeck, G.J.: Value maps: finding value in markets that are expensive. In: Oja, E., Kaski, S. (eds.) Kohonen Maps, pp. 15–32. Elsevier Science B.V. (1999)
Vesanto, J., Alhoniemi, E.: Clustering of the self-organizing map. IEEE Trans. Neural Networks 11(3), 586–600 (2000)
Migdał-Najman, K., Najman, K.: Applying the Kohonen self-organizing map networks to select variables. In: Preisach, C., Burkhardt, H., Schmidt-Thieme, L., Decker, R. (eds.) Data Analysis, Machine Learning and Applications, Studies in Classification, Data Analysis and Knowledge Organization, pp. 45–54. Springer (2008)
Kohonen, T.: Self-Organizing Maps. Springer, Berlin (1995)
Antonowicz, P., Szarmach, Ł.: Teoria i praktyka funkcjonowania piramidy finansowej versus studium przypadku upadłości Amber Gold Sp. z o.o., “Zarządzanie i Finanse. J. Manage. Finance” 11, 1/2 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Migdał-Najman, K., Najman, K., Antonowicz, P. (2019). Early Warning Against Insolvency of Enterprises Based on a Self-learning Artificial Neural Network of the SOM Type. In: Tarczyński, W., Nermend, K. (eds) Effective Investments on Capital Markets. Springer Proceedings in Business and Economics. Springer, Cham. https://doi.org/10.1007/978-3-030-21274-2_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-21274-2_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-21273-5
Online ISBN: 978-3-030-21274-2
eBook Packages: Economics and FinanceEconomics and Finance (R0)